Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bfs
    -0.08
    Students
    -0.08
    _PATTERN
    -0.07
    _ctor
    -0.07
    Aws
    -0.07
     הבריאות
    -0.07
    Five
    -0.06
    ลงทะเบ
    -0.06
    南宁市
    -0.06
    -api
    -0.06
    POSITIVE LOGITS
     treaty
    0.07
    仍然
    0.07
    的小
    0.07
    之美
    0.07
    ","","
    0.07
     물
    0.07
     emot
    0.07
    סה
    0.07
     trị
    0.07
    钿
    0.07
    Act Density 0.255%

    No Known Activations